AI embeddings backfill rake aborted

Привет :wave:

Я начал использовать Discourse AI с OpenAI API. Сначала я настроил его для связанных тем (text-embedding-ada-002). Когда я попытался запустить задачу rake для заполнения, получил следующую ошибку.

....rake aborted!
NoMethodError: undefined method `[]' for nil:NilClass (NoMethodError)

          response[:data].first[:embedding]
                  ^^^^^^^
/var/www/discourse/plugins/discourse-ai/lib/embeddings/vector_representations/text_embedding_ada_002.rb:37:in `vector_from'
/var/www/discourse/plugins/discourse-ai/lib/embeddings/vector_representations/base.rb:145:in `generate_representation_from'
/var/www/discourse/plugins/discourse-ai/lib/tasks/modules/embeddings/database.rake:19:in `block (2 levels) in <main>'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:71:in `each'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:71:in `block in find_each'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:138:in `block in find_in_batches'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:245:in `block in in_batches'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:229:in `loop'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:229:in `in_batches'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:137:in `find_in_batches'
/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:70:in `find_each'
/var/www/discourse/plugins/discourse-ai/lib/tasks/modules/embeddings/database.rake:17:in `block in <main>'
/usr/local/bin/bundle:25:in `load'
/usr/local/bin/bundle:25:in `<main>'
Tasks: TOP => ai:embeddings:backfill

Также в /logs я вижу следующее:
Screenshot 2024-01-27 at 7.09.32

Спасибо за помощь! :slightly_smiling_face:

Похоже, вы получаете пустой ответ.

Проверили ли вы ai embeddings enabled и добавили ли свой API-ключ в настройки?

Да, вот как выглядят настройки.

Screenshot 2024-01-27 at 9.08.56
Screenshot 2024-01-27 at 9.07.17


Задача Jobs::EmbeddingsBackfill, похоже, выполняется, но постоянно завершается ошибкой, о которой я упоминал в первом сообщении.
Screenshot 2024-01-27 at 9.11.36

Похоже, это связано с OpenAI.

Думаю, проблема была в лимите запросов. Мне пришлось повысить тарифный план в OpenAI и изменить модель на text-embedding-3-large. Теперь во время выполнения rake-задачи появляется много точек, что является хорошим признаком. :sweat_smile: Обновлю этот пост, когда всё будет завершено.

Редакция 1: Так что после 10 часов появления точек процесс завершился с ошибкой: rake aborted
rake aborted!

Faraday::TimeoutError: Net::ReadTimeout with #<TCPSocket:(closed)> (Faraday::TimeoutError)

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-protocol-0.2.2/lib/net/protocol.rb:229:in `rbuf_fill'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-protocol-0.2.2/lib/net/protocol.rb:199:in `readuntil'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-protocol-0.2.2/lib/net/protocol.rb:209:in `readline'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http/response.rb:158:in `read_status_line'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http/response.rb:147:in `read_new'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http.rb:2342:in `block in transport_request'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http.rb:2333:in `catch'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http.rb:2333:in `transport_request'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http.rb:2306:in `request'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/rack-mini-profiler-3.3.0/lib/patches/net_patches.rb:19:in `block in request_with_mini_profiler'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/rack-mini-profiler-3.3.0/lib/mini_profiler/profiling_methods.rb:50:in `step'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/rack-mini-profiler-3.3.0/lib/patches/net_patches.rb:18:in `request_with_mini_profiler'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-net_http-3.1.0/lib/faraday/adapter/net_http.rb:113:in `block in request_with_wrapped_block'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http.rb:1570:in `start'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-net_http-3.1.0/lib/faraday/adapter/net_http.rb:112:in `request_with_wrapped_block'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-net_http-3.1.0/lib/faraday/adapter/net_http.rb:102:in `perform_request'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-net_http-3.1.0/lib/faraday/adapter/net_http.rb:66:in `block in call'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-2.9.0/lib/faraday/adapter.rb:45:in `connection'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-net_http-3.1.0/lib/faraday/adapter/net_http.rb:65:in `call'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-2.9.0/lib/faraday/request/url_encoded.rb:25:in `call'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-2.9.0/lib/faraday/rack_builder.rb:152:in `build_response'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-2.9.0/lib/faraday/connection.rb:444:in `run_request'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-2.9.0/lib/faraday/connection.rb:280:in `post'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-2.9.0/lib/faraday.rb:145:in `method_missing'

/var/www/discourse/plugins/discourse-ai/lib/inference/open_ai_embeddings.rb:18:in `perform!'

/var/www/discourse/plugins/discourse-ai/lib/embeddings/vector_representations/text_embedding_3_large.rb:39:in `vector_from'

/var/www/discourse/plugins/discourse-ai/lib/embeddings/vector_representations/base.rb:147:in `generate_representation_from'

/var/www/discourse/plugins/discourse-ai/lib/tasks/modules/embeddings/database.rake:30:in `block (2 levels) in <main>'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:71:in `each'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:71:in `block in find_each'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:138:in `block in find_in_batches'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:245:in `block in in_batches'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:229:in `loop'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:229:in `in_batches'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:137:in `find_in_batches'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:70:in `find_each'

/var/www/discourse/plugins/discourse-ai/lib/tasks/modules/embeddings/database.rake:28:in `block in <main>'

/usr/local/bin/bundle:25:in `load'

/usr/local/bin/bundle:25:in `<main>'

Caused by:

Net::ReadTimeout: Net::ReadTimeout with #<TCPSocket:(closed)> (Net::ReadTimeout)

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-protocol-0.2.2/lib/net/protocol.rb:229:in `rbuf_fill'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-protocol-0.2.2/lib/net/protocol.rb:199:in `readuntil'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-protocol-0.2.2/lib/net/protocol.rb:209:in `readline'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http/response.rb:158:in `read_status_line'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http/response.rb:147:in `read_new'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http.rb:2342:in `block in transport_request'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http.rb:2333:in `catch'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http.rb:2333:in `transport_request'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http.rb:2306:in `request'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/rack-mini-profiler-3.3.0/lib/patches/net_patches.rb:19:in `block in request_with_mini_profiler'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/rack-mini-profiler-3.3.0/lib/mini_profiler/profiling_methods.rb:50:in `step'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/rack-mini-profiler-3.3.0/lib/patches/net_patches.rb:18:in `request_with_mini_profiler'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-net_http-3.1.0/lib/faraday/adapter/net_http.rb:113:in `block in request_with_wrapped_block'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/net-http-0.4.1/lib/net/http.rb:1570:in `start'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-net_http-3.1.0/lib/faraday/adapter/net_http.rb:112:in `request_with_wrapped_block'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-net_http-3.1.0/lib/faraday/adapter/net_http.rb:102:in `perform_request'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-net_http-3.1.0/lib/faraday/adapter/net_http.rb:66:in `block in call'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-2.9.0/lib/faraday/adapter.rb:45:in `connection'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-net_http-3.1.0/lib/faraday/adapter/net_http.rb:65:in `call'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-2.9.0/lib/faraday/request/url_encoded.rb:25:in `call'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-2.9.0/lib/faraday/rack_builder.rb:152:in `build_response'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-2.9.0/lib/faraday/connection.rb:444:in `run_request'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-2.9.0/lib/faraday/connection.rb:280:in `post'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/faraday-2.9.0/lib/faraday.rb:145:in `method_missing'

/var/www/discourse/plugins/discourse-ai/lib/inference/open_ai_embeddings.rb:18:in `perform!'

/var/www/discourse/plugins/discourse-ai/lib/embeddings/vector_representations/text_embedding_3_large.rb:39:in `vector_from'

/var/www/discourse/plugins/discourse-ai/lib/embeddings/vector_representations/base.rb:147:in `generate_representation_from'

/var/www/discourse/plugins/discourse-ai/lib/tasks/modules/embeddings/database.rake:30:in `block (2 levels) in <main>'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:71:in `each'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:71:in `block in find_each'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:138:in `block in find_in_batches'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:245:in `block in in_batches'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:229:in `loop'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:229:in `in_batches'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:137:in `find_in_batches'

/var/www/discourse/vendor/bundle/ruby/3.2.0/gems/activerecord-7.0.8/lib/active_record/relation/batches.rb:70:in `find_each'

/var/www/discourse/plugins/discourse-ai/lib/tasks/modules/embeddings/database.rake:28:in `block in <main>'

/usr/local/bin/bundle:25:in `load'

/usr/local/bin/bundle:25:in `<main>'

Tasks: TOP => ai:embeddings:backfill

(See full trace by running task with --trace)

Я перезапустил rake. В этом случае будут обработаны только необработанные темы или снова все темы? :smile:

Редакция 2: rake снова завершился с ошибкой с тем же сообщением. Но я думаю, что эти процессы охватили большинство тем, и Jobs::EmbeddingsBackfill в Sidekiq теперь, похоже, работает нормально. Так что, возможно, этого будет достаточно для оставшихся тем :slight_smile: